Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4080 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.3352. Min Act: -0.1700
Data Index: 3212587 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2881. Min Act: -0.1700
Data Index: 6913514 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2724. Min Act: -0.1700
Data Index: 3158193 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2567. Min Act: -0.1700
Data Index: 6736732 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2567. Min Act: -0.1700
Data Index: 1455470 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2567. Min Act: -0.1700
Data Index: 2371005 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2567. Min Act: -0.1700
Data Index: 6954842 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2567. Min Act: -0.1700
Data Index: 1262736 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2724. Min Act: -0.1700
Data Index: 8043810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2410. Min Act: -0.1700
Data Index: 3143062 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2410. Min Act: -0.1700
Data Index: 3540063 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2410. Min Act: -0.1700
Data Index: 3212588 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2410. Min Act: -0.1700
Data Index: 3779224 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2410. Min Act: -0.1700
Data Index: 1799873 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2410. Min Act: -0.1700
Data Index: 2959334 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2410. Min Act: -0.1700
Data Index: 102907 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2567. Min Act: -0.1700
Data Index: 6736733 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2567. Min Act: -0.1700
Data Index: 6546912 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2253. Min Act: -0.1700
Data Index: 2256095 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3352. Min Range: -3.3352
Max Act: 3.2253. Min Act: -0.1700
Data Index: 985360 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19